© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21046
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the action of granting or bestowing something

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -1.04
    expandindo
    -0.88
    BeginContext
    -0.88
    PerformLayout
    -0.88
     resourceCulture
    -0.86
    ])));
    -0.86
     JAXBElement
    -0.85
    ,:);
    -0.84
     Paglinawan
    -0.82
    Portail
    -0.81
    POSITIVE LOGITS
    itex
    0.49
    ü
    0.47
     Fig
    0.47
     I
    0.46
     contact
    0.46
    ocell
    0.44
     null
    0.42
     cell
    0.42
    stellung
    0.41
     Haye
    0.40
    Activations Density 0.000%

    No Known Activations